© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75077
    Prev
    Next
    INDEX
    Explanations

    written information

    np_acts-logits-general · gemini-2.5-flash-lite

    realistically

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lerinin
    0.55
    lerini
    0.52
    キ
    0.52
     decirlo
    0.50
    lä
    0.49
    ﾗ
    0.49
    lini
    0.46
     お
    0.46
    сер
    0.46
    lás
    0.46
    POSITIVE LOGITS
    PADDING
    0.46
    NEE
    0.45
    τική
    0.42
     yal
    0.41
     ဒါ
    0.40
     NA
    0.39
    具备
    0.39
     nee
    0.39
     dokon
    0.38
    conditioning
    0.38
    Activations Density 0.000%

    No Known Activations